Is it September yet? Hardly! School is barely out for the summer. But according to Google and Quantum Metric research, the back-to-school and off-to-college shopping season – which in the U.S. is second only to the holidays in terms of purchasing volume1 – has already begun. For retailers, that means planning for this peak season has kicked off as well.

We’d like to share four key trends that emerged from Google research and Quantum Metric’s Back-to-School Retail Benchmarks study of U.S. retail data, explore the reasons behind them, and outline the key takeaways.

1. Out-of-stock and inflation concerns are changing the way consumers shop. Back-to-school shoppers are starting earlier every year, with 41% beginning even before school is out – even more so when buying for college1. Why? The behavior is driven in large part by consumers’ concerns that they won’t be able to get what they need if they wait too long. 29% of shoppers start looking a full month before they need something1.

Back-to-school purchasing volume is quite high, with the majority spending up to $500 and 21% spending more than $1,0001. In fact, looking at year-over-year data, we see that average cart values have not only doubled since November 2021, but increased since the holidays1. And keep in mind that back-to-school spending is a key indicator leading into the holiday season.

That said, as people are reacting to inflation, they are comparing prices, hunting for bargains, and generally taking more time to plan. This is borne out by the fact that 76% of online shoppers are adding items to their carts and waiting to see if they go on sale before making the purchase1. And, to help stay on budget and reduce shipping costs, 74% plan to make multiple purchases in one checkout1. That carries over to in-store shopping, when consumers are buying more in one visit to reduce trips and save on gas.

2. The omnichannel theme continues. Consumers continue to use multiple channels in their shopping experience. As the pandemic has abated, some 82% expect that their back-to-school buying will be in-store, and 60% plan to purchase online. But in any case, 45% of consumers report that they will use both channels; more than 50% research online first before ever setting foot in a store2. Some use as many as five channels, including video and social media, and these 54% of consumers spend 1.5 times more compared to those who use only two channels4.

And mobile is a big part of the journey. Shoppers are using their phones to make purchases, especially for deadline-driven, last-minute needs, and often check prices on other retailers’ websites while shopping in-store. Anecdotally, mobile is a big part of how we ourselves shop with our children, who like to swipe on the phone through different options for colors and styles. We use our desktops when shopping on our own, especially for items that require research and represent a larger investment – and our study shows that’s quite common.

3. Consumers are making frequent use of wish lists. One trend we have observed is a higher abandonment rate, especially for apparel and general home and school supplies, compared to bigger-ticket items that require more research. But that can be attributed in part to the increasing use of wish lists. Online shoppers are picking a few things that look appealing or items on sale, saving them in wish lists, and then choosing just a few to purchase. Our research shows that 39% of consumers build one or two wish lists per month, while 28% said they build one or two each week, often using their lists to help with budgeting1.

4. Frustration rates have dropped significantly. Abandonment rates aside, shopper annoyance rates are down by 41%, year over year1. This is despite out-of-stock concerns and higher prices. But one key finding showed that both cart abandonment and “rage clicks” are more frequent on desktops, possibly because people investing time on search also have more time to complain to customer service.

And frustration does still exist. Some $300 billion is lost each year in the U.S. from bad search experiences5. Data collected internationally shows that 80% of consumers view a brand differently after experiencing search difficulties, and 97% favor websites where they can quickly find what they are looking for5.

Lessons to Learn

What are the key takeaways for retailers? In general, consider the sources of customer pain points and find ways to erase friction. Improve search and personalization. And focus on improving the customer experience and building loyalty. Specifically:

80% of shoppers want personalization6. Think about how you can drive personalized promotions or experiences that will drive higher engagement with your brand.

46% of consumers want more time to research1. Drive toward providing more robust research and product information points, like comparison charts, images, and specific product details.

43% of consumers want a discount1, but given current economic trends, retailers may not be offering discounts. In order to appease budget-conscious shoppers, retailers can consider other retention strategies such as driving loyalty using points, rewards, or faster-shipping perks.

Be sure to keep returns as simple as possible so consumers feel confident when making a purchase, and reduce possible friction points if a consumer decides to make a return. 43% of shoppers return at least a quarter of the products they buy and do not want to pay for shipping or jump through hoops1.

How We Can Help

Google-sponsored research shows that price, deals, and promotions are important to 68% of back-to-school shoppers.7 In addition, shoppers want certainty that they will get what they want. Google Cloud can make it easier for retailers to enable customers to find the right products with discovery solutions. These solutions provide Google-quality search and recommendations on a retailer’s own digital properties, helping to increase conversions and reduce search abandonment. In addition, Quantum Metric solutions, available on the Google Cloud Marketplace, are built with BigQuery, which helps retailers consolidate and unlock the power of their raw data to identify areas of friction and deliver improved digital shopping experiences.

We invite you to watch the Total Retail webinar “4 ways retailers can get ready for back-to-school, off-to college” on demand and to view the full Back-to-School Retail Benchmarks report from Quantum Metric.

Sources:
1. Back-to-School Retail Benchmarks report from Quantum Metric
2. Google/Ipsos,Moments 2021, Jun 2021, Online survey, US, n=335 Back to School shoppers
3. Google/Ipsos, Moments 2021, Jun 2021, Online survey, US, n=2,006 American general population 18+
4. Google/Ipsos, Holiday Shopping Study, Oct 2021 – Jan 2022, Online survey, US, n=7,253, Americans 18+ who conducted holiday shopping activities in past two days
5. Google Cloud Blog, Nov 2021, “Research: Search abandonment has a lasting impact on brand loyalty”
6. McKinsey & Company, “Personalizing the customer experience: Driving differentiation in retail”
7. Think with Google, July 2021, “What to expect from shoppers this back-to-school season”

Explainable AI (XAI) helps you understand and interpret how your machine learning models make decisions. We’re excited to announce that BigQuery Explainable AI is now generally available (GA). BigQuery is the data warehouse that supports explainable AI in a most comprehensive way w.r.t both XAI methodology and model types. It does this at BigQuery scale, enabling millions of explanations within seconds with a single SQL query.

Why is Explainable AI so important? To demystify the inner workings of machine learning models, Explainable AI is quickly becoming an essential and growing need for businesses as they continue to invest in AI and ML. With 76% of enterprises now prioritizing artificial intelligence (AI) and machine learning (ML) over other initiatives in 2021 IT budgets, the majority of CEOs (82%) believe that AI-based decisions must be explainable to be trusted according to a PwC survey.

While the focus of this blogpost is on BigQuery Explainable AI, Google Cloud provides a variety of tools and frameworks to help you interpret models outside of BigQuery, such as with Vertex Explainable AI, which includes AutoML Tables, AutoML Vision, and custom-trained models.

So how does Explainable AI in BigQuery work exactly? And how might you use it in practice? 

Two types of Explainable AI: global and local explainability

When it comes to Explainable AI, the first thing to note is that there are two main types of explainability as they relate to the features used to train the ML model: global explainability and local explainability.

Imagine that you have a ML model that predicts housing price (as a dollar amount), based on three features: (1) number of bedrooms, (2) distance to the nearest city center, and (3) construction date.

Global explainability (a.k.a. global feature importance) describes the features’ overall influence on the model and helps you understand if a feature had a greater influence than other features over the model’s predictions. For example, global explainability can reveal that the number of bedrooms and distance to city center typically has a much stronger influence than the construction date on predicting housing prices. Global explainability is especially useful if you have hundreds or thousands of features and you want to determine which features are the most important contributors to your model. You may also consider using global explainability as a way to identify and prune less important features to improve the generalizability of their models.

Local explainability (a.k.a. feature attributions) describes the breakdown of how each feature contributes towards a specific prediction. For example, if the model predicts that house ID#1001 has a predicted price of $230,000, local explainability would describe a baseline amount (e.g. $50,000) and how each of the features contributes on top of the baseline towards the predicted price. For example, the model may say that on top of the baseline of $50,000, having 3 bedrooms contributed an additional $50,000, close proximity to the city center added $100,000, and construction date of 2010 added $30,000, for a total predicted price of $230,000. In essence, understanding the exact contribution of each feature used by the model to make each prediction is the main purpose of local explainability.

What ML models does BigQuery Explainable AI apply to?

BigQuery Explainable AI applies to a variety of models, including supervised learning models for IID data and time series models. The documentation for BigQuery Explainable AI provides an overview of the different ways of applying explainability per model. Note that each explainability method has its own way of calculation (e.g. Shapley values), which are covered more in-depth in the documentation.

Examples with BigQuery Explainable AI

In this next section, we will show three examples of how to use BigQuery Explainable AI in different ML applications: 

• regression 
• classification
• time-series forecasting

Regression models with BigQuery Explainable AI

Let’s use a boosted tree regression model to predict how much a taxi cab driver will receive in tips for a taxi ride, based on features such as number of passengers, payment type, total payment and trip distance. Then let’s use BigQuery Explainable AI to help us understand how the model made the predictions in terms of global explainability (which features were most important?) and local explainability (how did the model arrive at each prediction?).

The taxi trips dataset comes from the BigQuery public datasets and is publicly available in the table: bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018. 

First, you can train a boosted tree regression model.

  CREATE OR REPLACE MODEL bqml_tutorial.taxi_tip_regression_model
OPTIONS (model_type='boosted_tree_regressor',
         input_label_cols=['tip_amount'],
         max_iterations = 50,
         tree_method = 'HIST',
         subsample = 0.85,
         enable_global_explain = TRUE
) AS
SELECT
  vendor_id,
  passenger_count,
  trip_distance,
  rate_code,
  payment_type,
  total_amount,
  tip_amount
FROM
  `bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018`
WHERE tip_amount >= 0
LIMIT 1000000

Now let’s do a prediction using ML.PREDICT, which is the standard way in BigQuery ML to make predictions without explainability.

  SELECT *
FROM
ML.PREDICT(MODEL bqml_tutorial.taxi_tip_regression_model,
 (
 SELECT
   "0" AS vendor_id,
   1 AS passenger_count,
   CAST(5.85 AS NUMERIC) AS trip_distance,
   "0" AS rate_code,
   "0" AS payment_type,
   CAST(55.56 AS NUMERIC) AS total_amount))

But you might wonder—how did the model generate this prediction of ~11.077?

BigQuery Explainable AI can help us answer this question. Instead of using ML.PREDICT, you use ML.EXPLAIN_PREDICT with an additional optional parameter top_k_features. ML.EXPLAIN_PREDICT extends the capabilities of ML.PREDICT by outputting several additional columns that explain how each feature contributes to the predicted value. In fact, since ML.EXPLAIN_PREDICT includes all the output from ML.PREDICT anyway, you may want to consider using ML.EXPLAIN_PREDICT every time instead.

  SELECT *
FROM
ML.EXPLAIN_PREDICT(MODEL bqml_tutorial.taxi_tip_regression_model,
 (
 SELECT
   "0" AS vendor_id,
   1 AS passenger_count,
   CAST(5.85 AS NUMERIC) AS trip_distance,
   "0" AS rate_code,
   "0" AS payment_type,
   CAST(55.56 AS NUMERIC) AS total_amount),
 STRUCT(6 AS top_k_features))

The way to interpret these columns is:

Σfeature_attributions + baseline_prediction_value = prediction_value

Let’s break this down. The prediction_value is ~11.077, which is simply the predicted_tip_amount. The baseline_prediction_value is ~6.184, which is the tip amount for an average instance. top_feature_attributions indicates how much each of the features contributes towards the prediction value. For example, total_amount contributes ~2.540 to the predicted_tip_amount. 

ML.EXPLAIN_PREDICT provides local feature explainability for regression models. For global feature importance, see the documentation for ML.GLOBAL_EXPLAIN.

Classification models with BigQuery Explainable AI

Let’s use a logistic regression model to show you an example of BigQuery Explainable AI with classification models. We can use the same public dataset as before: bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018.

Train a logistic regression model to predict the bracket of the percentage of the tip amount out of the taxi bill.

  CREATE OR REPLACE MODEL bqml_tutorial.taxi_tip_classification_model
OPTIONS
 (model_type='logistic_reg',
  input_label_cols=['tip_bucket'],
  enable_global_explain=true
) AS
SELECT
  vendor_id,
  passenger_count,
  trip_distance,
  rate_code,
  payment_type,
  total_amount,
  CASE
    WHEN tip_amount > total_amount*0.20 THEN '20% or more'
    WHEN tip_amount > total_amount*0.15 THEN '15% to 20%'
    WHEN tip_amount > total_amount*0.10 THEN '10% to 15%'
  ELSE '10% or less'
  END AS tip_bucket
FROM
  `bigquery-public-data.new_york_taxi_trips.tlc_yellow_trips_2018`
WHERE tip_amount >= 0
LIMIT 1000000

Next, you can run ML.EXPLAIN_PREDICT to get both the classification results and the additional information for local feature explainability. For global explainability, you can use ML.GLOBAL_EXPLAIN. Again, since ML.EXPLAIN_PREDICT includes all the output from ML.PREDICT anyway, you may want to consider using ML.EXPLAIN_PREDICT every time instead.

  SELECT *
FROM
ML.EXPLAIN_PREDICT(MODEL bqml_tutorial.taxi_tip_classification_model,
 (
 SELECT
   "0" AS vendor_id,
   1 AS passenger_count,
   CAST(5.85 AS NUMERIC) AS trip_distance,
   "0" AS rate_code,
   "0" AS payment_type,
   CAST(55.56 AS NUMERIC) AS total_amount),
 STRUCT(6 AS top_k_features))

Similar to the regression example earlier, the formula is used to derive the prediction_value:

Σfeature_attributions + baseline_prediction_value = prediction_value

As you can see in the screenshot above, the baseline_prediction_value is ~0.296. total_amount is the most important feature in making this specific prediction, contributing ~0.067 to the prediction_value, though followed by trip_distance. The feature passenger_count contributes negatively to prediction_value by -0.0015. The features vendor_id, rate_code, and payment_type did not seem to contribute much to the prediction_value.

You may wonder why the prediction_value of ~0.389 doesn’t equal the probability value of  ~0.359. The reason is that unlike for regression models, for classification models, prediction_value is not a probability score. Instead, prediction_value is the logit value (i.e., log-odds) for the predicted class, which you could separately convert to probabilities by applying the softmax transformation to the logit values. For example, a three-class classification has a log-odds output of [2.446, -2.021, -2.190]. After applying the softmax transformation, the probability of these class predictions is [0.9905, 0.0056, 0.0038].

Time-series forecasting models with BigQuery Explainable AI

Explainable AI for forecasting provides more interpretability into how the forecasting model came to its predictions. Let’s go through an example of forecasting the number of bike trips in NYC using the new_york.citibike_trips public data in BigQuery.

You can train a time-series model ARIMA_PLUS:

  CREATE OR REPLACE MODEL bqml_tutorial.nyc_citibike_arima_model
OPTIONS
  (model_type = 'ARIMA_PLUS',
   time_series_timestamp_col = 'date',
   time_series_data_col = 'num_trips',
   holiday_region = 'US'
  ) AS
SELECT
   EXTRACT(DATE from starttime) AS date,
   COUNT(*) AS num_trips
FROM
  `bigquery-public-data.new_york.citibike_trips`
GROUP BY date

Next, you can first try forecasting without explainability using ML.FORECAST:
SELECT
  *
FROM
  ML.FORECAST(MODEL bqml_tutorial.nyc_citibike_arima_model,
              STRUCT(365 AS horizon, 0.9 AS confidence_level))

This function outputs the forecasted values and the prediction interval. Plotting it in addition to the input time series gives the following figure.

But how does the forecasting model arrive at its predictions? Explainability is especially important if the model ever generates unexpected results.

With ML.EXPLAIN_FORECAST, BigQuery Explainable AI provides extra transparency into the seasonality, trend, holiday effects, level (step) changes, and spikes and dips outlier removal. In fact, since ML.EXPLAIN_FORECAST includes all the output from ML.FORECAST anyway, you may want to consider using ML.EXPLAIN_FORECAST every time instead.

  SELECT
  *
FROM
  ML.EXPLAIN_FORECAST(MODEL bqml_tutorial.nyc_citibike_arima_model,
                      STRUCT(365 AS horizon, 0.9 AS confidence_level))

Compared to the previous figure which only shows the forecasting results, this figure shows much richer information to explain how the forecast is made.  

First, it shows how the input time series is adjusted by removing the spikes and dips anomalies, and by compensating the level changes. That is:

time_series_adjusted_data = time_series_data - spikes_and_dips - step_changes

Second, it shows how the adjusted input time series is decomposed into different components such as both weekly and yearly seasonal components, holiday effect component and trend component. That is

time_series_adjusted_data = trend + seasonal_period_yearly + seasonal_period_weekly + holiday_effect + residual

Finally, it shows how these components are forecasted separately to compose the final forecasting results. That is:

time_series_data = trend + seasonal_period_yearly + seasonal_period_weekly + holiday_effect

For more information on these time series components, please see the documentation here.

Conclusion

With the GA of BigQuery Explainable AI, we hope you will now be able to interpret your machine learning models with ease. 

Thanks to the BigQuery ML team, especially Lisa Yin, Jiashang Liu, Amir Hormati, Mingge Deng, Jerry Ye and Abhinav Khushraj. Also thanks to the Vertex Explainable AI team, especially David Pitman and Besim Avci.